Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnly, idempotent, and non-destructive hints, but the description adds valuable behavioral context beyond them: reading does not consume items, the same items return until they expire, and a lost response loses nothing. This meaningfully informs retry behavior and sets accurate agent expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, followed by constraints and cursor guidance, with most sentences earning their place. The standalone 'Read-only' sentence is somewhat redundant with the annotations and the opening verb, and the expiry sentence is slightly wordy, but overall it remains compact and well-ordered.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a low-complexity tool with rich annotations, full schema coverage, and an output schema, the description covers everything an agent needs: what data is returned, what is explicitly excluded, safety/retry semantics, and how to use the cursor. Nothing operationally critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents `limit` and `since` well. The description adds extra semantic value for `since` by explaining the retry pattern: 'Pass the returned cursor back as `since` to get only what is new,' which clarifies the pagination/incremental-read behavior beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Read items the user deliberately shared from their phone to you.' Concrete examples ('a link, a note, a snippet') and explicit non-goals (not text messages, notifications, or anything else) sharply distinguish it from sibling tools and make its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly defines when to use: when the user has explicitly shared an item via the phone's 'Share to Agents' action. It also states exclusions ('does NOT read their text messages, their notifications, or anything else'), which guides an agent away from other phone-access tools, though it does not name a specific sibling as the alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.